Written by: Philippe Menu, MD, Ph.D, MBA – EVP, Chief Medical Officer and Chief Product Officer, SOPHiA GENETICS
The Multimodal Imperative: How AI-Driven Technology is Driving Impactful Changes
In today’s fast-moving biopharma landscape, companies face increasing pressure to deliver the right treatment, to the right patient, at the right time, faster and more efficiently. As our understanding of disease biology complexity grows, legacy R&D models are increasingly strained to deliver timely and impactful innovations.
Just two decades ago, cancer was largely considered an organ-based disease. For example, lung cancer, despite known histological subtypes, was uniformly treated as a single disease — chemotherapy for all. Today, thanks to advances in clinical genomics, we recognize lung cancer as a collection of rare diseases, defined by a long tail of distinct genomic alterations. Targeted therapies have emerged to improve patient outcomes for eligible patients; however, high unmet medical needs remain. Most patients with metastatic lung cancer do not have a molecularly defined cause and are treated with immunotherapy as standard of care. Despite massive investments, single-biomarker approaches have repeatedly failed to reliably predict which patients will respond to immunotherapy.
To address these challenges, precision medicine must evolve from a siloed, single-biomarker approach to a more integrated, multimodal approach combining genomic, imaging, clinical, and biological data. Intuitively, taking a more holistic view of the patient, tumor, and host environment should open a stronger window into the biology of health and disease. However, to fully realize this potential, we must transform the data infrastructure that underpins precision medicine. This includes breaking down silos across data types, harmonizing and standardizing inputs, and fostering real-world knowledge sharing across institutions.
The Challenge of Unveiling Novel Insights
Over the past decade, we have seen a dual revolution in healthcare: the explosion of multiple types of digital health data being produced at scale in clinical routine (e.g., genomics, imaging, EHR entries) and generational breakthroughs in analytics capabilities (e.g., machine learning, foundational models). In theory, this combination should have unlocked the full potential of precision medicine, but in practice, we are arguably still at its Stone Age. One of the root causes is data fragmentation: healthcare data is still siloed, unharmonized, and difficult to integrate. The tools needed to bring these diverse data types together are often inadequate, and the ecosystem lacks strong incentives for large-scale data and insights sharing across institutions, while preserving privacy.
On the biopharma side, we see increasing interest and expertise for AI-driven approaches on specific data modalities (e.g., digital pathology), however, these initiatives are still rarely connected within a truly multimodal framework. Proprietary clinical trial databases, meanwhile, remain difficult to harmonize and merge together due to heterogeneous patient consent, compliance issues, and required investments.
What Happens When You Connect the Proverbial (Multimodal) Dots?
Multimodal AI-driven technology is already driving significant advances in our understanding of health and disease. By seamlessly integrating and analyzing diverse data sources, it enables a more holistic perspective of complex diseases like cancer, and the patient beyond the disease.
The practical application of AI-powered multimodal technology can help biopharma companies address drug development challenges and overall optimize this process (Figure 1).
Figure 1. Driving Efficiency Across the Drug Development Continuum with Multimodal AI-driven Technologies.
At SOPHiA GENETICS we believe that multimodal AI is no longer an option but a necessity to accelerate precision medicine. Our cloud-based SOPHiA DDM™ Platform seamlessly integrates and standardizes diverse data types into a unified analytical framework, comprising state-of-the-art specialized computational modules for data processing and analysis (e.g., genomics, radiomics), and a dedicated multimodal factory. This engine combines, extracts, and structures complex multimodal data to fuel the development of predictive analytics, delivering actionable insights that empower data-driven decision-making (Figure 2).
Figure 2. The SOPHiA DDM™ Platform enables the analysis of multimodal data at scale.
The potential of multimodal approaches is evident in the initiatives we are leading here at SOPHiA GENETICS, notably the TRIDENT project (Skoulidis et al, 2024). In this retrospective multimodal re-analysis of AstraZeneca’s Phase 3 POSEIDON trial (NCT03164616), AI-powered models were trained on integrated clinical trial data to predict treatment benefit. The goal was to identify patient subpopulations that may derive greater benefit from the addition of a CTLA-4 inhibitor to a PD-L1 and chemotherapy backbone in treatment-naïve metastatic lung cancer. These models yielded signatures identifying approximately 50% of the trial population in scope that would be predicted to benefit from the addition of CTLA-4 inhibition, with a hazard ratio reduction from 0.88 (95% CI, 0.68-1.12) to 0.56 (95% CI, 0.33-0.97) in the non-squamous histology population (Figure 3). These multimodal signatures are clinically interpretable and can be readily deployed in the real-world setting on the SOPHiA DDM™ Platform for further clinical research.
Figure 3. Multimodal re-analysis of the non-squamous patient population in the Phase 3 POSEIDON trial.
The Future of Precision Medicine is Multimodal
The transition from single-modality to multimodal AI-driven analysis represents a paradigm shift in precision medicine. Organizations that successfully integrate diverse data modalities and multimodal technology will be best positioned to drive better patient outcomes and maximize drug development success.
Realizing this potential, however, demands more than technical innovation. It demands systemic transformation across the healthcare landscape — from evolving regulatory frameworks for multimodal CDx to updated reimbursement models, standardized deployment practices, and greater education for both clinicians and patients.
For biopharma companies, the path forward is clear:
- Break Down Data Silos: Support the democratization of access to different data modalities, both in the real-world setting as well as in the clinical trial space.
- Invest in Multimodal Technology and Expertise: Partner with technology leaders to integrate multimodal approaches into drug development, go-to-market strategies, and post-marketing decision support.
- Foster Collaborations to Shape the Ecosystem: Engage with regulators, payors, academic institutions, and technology partners to validate, standardize, and endorse multimodal approaches.
About twenty years ago, cancer was still considered an organ disease. Looking back today, this may look like distant, medieval times. Twenty years from now, new generations of life sciences professionals may look at 2025 in a disturbingly similar way. The multimodal revolution is only getting started.
References
Skoulidis, F. et al. 1325P TRIDENT: Machine learning (ML) multimodal signatures to identify patients that would benefit most from Tremelimumab (T) addition to durvalumab (D) + chemotherapy (CT) with data from the POSEIDON trial. Ann. Oncol. 35, S842–S843 (2024).